Generative Dialogue Research Articles

Exploring the Role of Mobile Apps for Insomnia in Depression: Systematic Review.

The COVID-19 pandemic has profoundly affected mental health, leading to an increased prevalence of depression and insomnia. Currently, artificial intelligence (AI) and deep learning have thoroughly transformed health care-related mobile apps, offered more effective mental health support, and alleviated the psychological stress that may have emerged during the pandemic. Early reviews outlined the use of mobile apps for dealing with depression and insomnia separately. However, there is now an urgent need for a systematic evaluation of mobile apps that address both depression and insomnia to reveal new applications and research gaps. This study aims to systematically review and evaluate mobile apps targeting depression and insomnia, highlighting their features, effectiveness, and gaps in the current research. We systematically searched PubMed, Scopus, and Web of Science for peer-reviewed journal articles published between 2017 and 2023. The inclusion criteria were studies that (1) focused on mobile apps addressing both depression and insomnia, (2) involved young people or adult participants, and (3) provided data on treatment efficacy. Data extraction was independently conducted by 2 reviewers. Title and abstract screening, as well as full-text screening, were completed in duplicate. Data were extracted by a single reviewer and verified by a second reviewer, and risk of bias assessments were completed accordingly. Of the initial 383 studies we found, 365 were excluded after title, abstract screening, and removal of duplicates. Eventually, 18 full-text articles met our criteria and underwent full-text screening. The analysis revealed that mobile apps related to depression and insomnia were primarily utilized for early detection, assessment, and screening (n=5 studies); counseling and psychological support (n=3 studies); and cognitive behavioral therapy (CBT; n=10 studies). Among the 10 studies related to depression, our findings showed that chatbots demonstrated significant advantages in improving depression symptoms, a promising development in the field. Additionally, 2 studies evaluated the effectiveness of mobile apps as alternative interventions for depression and sleep, further expanding the potential applications of this technology. The integration of AI and deep learning into mobile apps, particularly chatbots, is a promising avenue for personalized mental health support. Through innovative features, such as early detection, assessment, counseling, and CBT, these apps significantly contribute toward improving sleep quality and addressing depression. The reviewed chatbots leveraged advanced technologies, including natural language processing, machine learning, and generative dialog, to provide intelligent and autonomous interactions. Compared with traditional face-to-face therapies, their feasibility, acceptability, and potential efficacy highlight their user-friendly, cost-effective, and accessible nature with the aim of enhancing sleep and mental health outcomes.

Possibilities and missed opportunities for generative dialogue: professional networking, online platforms and the English classroom

Possibilities and missed opportunities for generative dialogue: professional networking, online platforms and the English classroom

Hydro-Rugging as Reparative Caring Encounter: Re-Membering Southern Oceanic Hauntologies

ABSTRACT Expanding beach clean-ups to more than just removing plastic from the shoreline, citizens are invited to dwell with the ecological crisis and its intersectional entanglements of historical injustices related to the ocean, through a tactile mending practice using collected rubbish. Public story-doing (Rodricks, 2024) [Towards a (strategic) sensibility of unbelonging: Full participation revisited. International Journal of Qualitative Studies in Education, 1–15] is initiated by generative dialogue enabled through the material call of the collected plastic which is re-membered and mended into the Mother Hydro-rug. This making-with thinking/theorising (Haraway, 2016 [Staying with the trouble: Making kin in the Chthulucene. Duke University Press]; Manning, 2016 [The minor gesture. Duke University Press]) involves re-membering erased narratives that entangle people with the ocean. Hydro-rugging fosters reparative care practices within vulnerable communities through convivial organised events that bring together people, particularly Black and Brown bodies, together to share their memories of and with the ocean. Hydro-rugging embodies the importance of active listening and acknowledging emotions (Ahmed, 2004) [The cultural politics of emotion. University Press], engaging in a call and response with the very fabric of beach surroundings, be it the plastic or other more-than-human elements.

Safe Space for Dialogue—A Practice for Connected Consciousness and Compassion

This paper analyzes Safe Space for Dialogue as a group practice for accessing connected consciousness through the safe expression of emotional experience, empathic listening, and compassionate witnessing. It highlights the importance of connected consciousness to overcome architectures of separation that breed fear, isolation, domination, and instrumentalization of relationships. Connected consciousness is an intersubjective, relational experience that makes possible connection, compassion, and empathic and generative dialogue. This article offers an outline of the main qualities of connected consciousness—safety, empathy and compassion, attunement, and resonance; it analyzes how the practice of Safe Space for Dialogue develops expanded awareness and compassion, supporting participants’ access to the connected consciousness.

Didactic experiences in the public realm: AI, interactivity, and playfulness for empowering eco-change

ABSTRACT Artificial Intelligence (AI) rapidly adapts to diverse audience engagement modes in Digital Arts, either interactive or non-interactive forms. These engagements create potential alliances for intelligent eco-didactic environments in the public realm. Studies show that interactivity positively affects the learning experience; hence, the coalition between AI and Digital Art has the potential to result in enhanced eco-art experiences. This collaboration could augment the eco-message and lead to behavior shift. This paper explores the interactive engagement modes in different art mediums to identify their eco-didactic potential. The study adopts a mixed methods approach, engaging with causal-comparative qualitative content analysis research. We collected secondary data from various mediums to define the characteristics of the engagement modes in eco-art, digital art, and AI artworks. Finally, we interviewed mixed-media artists to explore the technologies used in these art mediums, the different engagement modes they adopt, and eco-didactic possibilities. As a result, we found that incorporating aspects such as interactivity, coherence, aesthetics, playfulness, and meaning, can increase the impact of eco-didactic experiences. In addition, AI creates new possibilities for these experiences with its popularity and features such as real-time data utilization, personalization, and generative reciprocal dialogues which facilitate the understanding of complex environmental issues.

Comparative study on personalized open-domain generative dialogue systems

Developing personalized dialogue systems is a monumental challenge in the rapidly evolving domain of Natural Language Processing (NLP). These systems are engineered to facilitate more natural, intuitive, and user-friendly interactions between humans and machines. Their theoretical significance extends to real-world applications, making them an invaluable asset in today's digital age. Over recent years, this area has garnered immense attention from researchers and academics, becoming a hotbed for innovation and study. This paper aims to contribute to this burgeoning field by conducting an in-depth comparative analysis of the current leading personalized language models. Specifically, this paper will scrutinize models grounded in deep learning algorithms and those that employ reinforcement learning techniques. This research objective is to dissect each approach's unique advantages and limitations. By doing so, the paper hopes to identify actionable avenues for improvement and optimization. Furthermore, the paper will offer a forward-looking perspective, outlining potential advancements and innovations that could shape the future landscape of personalized dialogue systems in Natural Language Processing.

Youth and Community Work for Climate Justice: Towards an Ecocentric Ethics for Practice

ABSTRACT This paper traces an expanded ethical perspective for youth and community work (YCW) practice in response to the climate and biodiversity crises. Discussing ecological ethics, we problematise the liberal humanist emphasis on utilitarianism and reject it as inappropriate for YCW in these times. Instead, we argue for an ecocentric practice ethic which intrinsically values the non-human world. To advance an ecocentric ethical perspective for YCW we draw on decolonial and posthuman theory. Inspired by a Freirean dialogical approach, we apply these theoretical domains as lenses to problematise YCW practice, seeking a generative dialogue between perspectives. Through this, we identify three emergent tasks for ecocentric YCW: (a) thinking and acting beyond the individual; (b) cultivating reciprocal care and connection and (c) practicing critical pedagogies of place. This third element builds on YCW's social pedagogic tradition and provides a practical means to incorporate ecocentric ideas into practice. We conclude that, given the unprecedented implications of climate crises and biodiversity collapse, a YCW ethics that does not consider these implications for young people is insufficient for the context of practice today. Enacting an ecocentric YCW ethics requires ongoing collective praxis and dialogue between young people, practitioners, educators, managers and students.

Sounds of Life and Concern: Echoing Through Lively Storytelling in Early Childhood Education

This paper emerges from the journey of a group of early childhood educators seeking to reconnect with land in meaningful and ethical ways. Reorienting from humancentric views, the authors explore “lively storytelling” to bring attention to overlooked stories and create alternative ways of being and thinking. We are called into new relations and ecological entanglements through a sensitive and responsive attunement to the soundscapes of Lynn Creek and Hastings Creek in Vancouver and Bow River in Calgary. Our engagement encompasses a posthumanist framework while weaving interdisciplinary studies in environmental humanities, materiality, and architecture to encourage generative inquiries and dialogue in early childhood classrooms and communities.

Generative Artificial Intelligence and Generative Conversations: Contrasting Futures for Organizational Change?

To what extent are “generative AI” (as a machine-based form of decision-making) and “generative dialogue” (as a human-based form of decision-making) complimentary or competing? What takes precedence in generative change processes? More fundamentally, should generative artificial intelligence (AI) processes assist human decision-making or should human processes assist generative AI decision-making? The possible implications of these questions are explored. Moreover, it is posited that as generative AI evolves and gains more traction in organizational change initiatives, it is important that it is deployed in ways that support generative conversations rather than ways that undermine or replace them.

Can Artificial Intelligence Improve the Readability of Patient Education Materials on Aortic Stenosis? A Pilot Study.

The advent of generative artificial intelligence (AI) dialogue platforms and large language models (LLMs) may help facilitate ongoing efforts to improve health literacy. Additionally, recent studies have highlighted inadequate health literacy among patients with cardiac disease. The aim of the present study was to ascertain whether two freely available generative AI dialogue platforms could rewrite online aortic stenosis (AS) patient education materials (PEMs) to meet recommended reading skill levels for the public. Online PEMs were gathered from a professional cardiothoracic surgical society and academic institutions in the USA. PEMs were then inputted into two AI-powered LLMs, ChatGPT-3.5 and Bard, with the prompt "translate to 5th-grade reading level". Readability of PEMs before and after AI conversion was measured using the validated Flesch Reading Ease (FRE), Flesch-Kincaid Grade Level (FKGL), Simple Measure of Gobbledygook Index (SMOGI), and Gunning-Fog Index (GFI) scores. Overall, 21 PEMs on AS were gathered. Original readability measures indicated difficult readability at the 10th-12th grade reading level. ChatGPT-3.5 successfully improved readability across all four measures (p < 0.001) to the approximately 6th-7th grade reading level. Bard successfully improved readability across all measures (p < 0.001) except for SMOGI (p = 0.729) to the approximately 8th-9th grade level. Neither platform generated PEMs written below the recommended 6th-grade reading level. ChatGPT-3.5 demonstrated significantly more favorable post-conversion readability scores, percentage change in readability scores, and conversion time compared to Bard (all p < 0.001). AI dialogue platforms can enhance the readability of PEMs for patients with AS but may not fully meet recommended reading skill levels, highlighting potential tools to help strengthen cardiac health literacy in the future.

Design of Improved Artificial Intelligence Generative Dialogue Algorithm and Dialogue System Model Based on Knowledge Graph

Design of Improved Artificial Intelligence Generative Dialogue Algorithm and Dialogue System Model Based on Knowledge Graph

Диалог поколений и тема памяти в рассказах Юрия Яковлева о Великой Отечественной войне

В центре нашего внимания произведения Ю. Я. Яковлева, востребованные в школьном литературоведении, обладающие воспитательным потенциалом, однако недостаточно исследованные литературоведами. Обзор статей, посвященных рассказам писателя о Великой Отечественной войне, позволяет выделить их общие особенности: центральными являются мотив памяти и прием ретроспекции, обеспечивающие смычку двух временных пластов – 1940-х и 1960-х гг.; значимость диалогов персонажей разных поколений, внимание к внутреннему миру человека. Цель статьи – исследовать тему памяти и своеобразие межпоколенческого диалога в двух практически не исследованных ранее рассказах Юрия Яковлева 1970-х гг., посвященных Великой Отечественной войне. Литературный материал («Девочки с Васильевского острова», «Память») интерпретирован с опорой на структурно-семиотический метод исследования. Писатель использует ряд художественных приемов: ретроспекцию, соположение двух пространственно-временных планов (война и современность), в центре – пара персонажей «ребенок – взрослый» или «ребенок – ребенок», первый представляет послевоенное поколение и является носителем знания о войне или инициирует получение этого знания, а второй – имеющий непосредственный опыт войны/блокады. Ю. Яковлев раскрывает идею духовного родства, нерушимой связи фронтового и послевоенных поколений. Ребенок у Яковлева является хранителем памяти и транслятором знаний о войне. Для того чтобы погибшие продолжили жить в памяти своих духовных потомков, необходимы личные усилия, проявление настойчивости и храбрости. Писатель наследует некоторые черты «лейтенантской прозы» (лаконизм повествования, внимание к внутреннему миру персонажа, соединение лиризма, психологизма и натурализма). Вместе с тем есть отличия, что обусловлено временем создания текстов – 1970-е гг. Изображение событий 1940-х гг. опосредовано сознанием и воображением персонажей-детей, родившихся уже после войны, а значит, не могущих быть непосредственными свидетелями или носителями военного опыта. Эта особенность позволяет трактовать рассказы Ю. Яковлева в контексте концепции «постпамяти», обоснованной М. Хирш. The focus of our attention is on the works of Yu. Ya. Yakovlev, which are in demand in school literary studies, have educational potential, but are insufficiently studied by literary critics. A review of articles devoted to the writer’s stories about the Great Patriotic War allows us to highlight their common features: central are the motif of memory and the technique of retrospection, providing a “link” of two time layers – the 1940s and the present (for the characters); the importance of dialogues of characters of different generations, attention to the inner world of characters. The article explores the theme of memory and the peculiarity of intergenerational dialogue in the works of Yuri Yakovlev of the 1970s, dedicated to the Great Patriotic War. The literary material (“Girls from Vasilievsky Island”, “Memory”) is interpreted based on the structural-semiotic research method. The writer uses a number artistic techniques: retrospection, the juxtaposition of two space-time planes (war and modernity), in the center – a pair of characters “child-adult” or “child-child”, the first represents the post-war generation and is the bearer of knowledge about the war or initiates the acquisition of this knowledge, and the second - having direct experience wars/blockades. Yu. Yakovlev reveals the idea of spiritual kinship, the unbreakable bond of the front-line and post-war generations. In order for the deceased to continue to live in the memory of their spiritual descendants, personal efforts, work and courage are needed to preserve knowledge about the war, loyalty to friendship. The analysis of the stories makes it clear that the writer inherits some features of the “lieutenant’s prose” (laconism of narration, attention to the inner world of the character, reliance on documentalism, a combination of lyricism, psychologism and naturalism). At the same time, there are differences due to the time of the creation of texts – the 1970s. The depiction of the events of the 1940s is mediated by the consciousness and imagination of the characters-children born after the war, which means they cannot be direct witnesses or bearers of military experience. This feature allows you to interpret the stories of Yu. Yakovlev in the context of the concept of “post-memory”, justified by M. Hirsch.

Design of a Modified Transformer Architecture Based on Relative Position Coding

Natural language processing (NLP) based on deep learning provides a positive performance for generative dialogue system, and the transformer model is a new boost in NLP after the advent of word vectors. In this paper, a Chinese generative dialogue system based on transformer is designed, which only uses a multi-layer transformer decoder to build the system and uses the design of an incomplete mask to realize one-way language generation. That is, questions can perceive context information in both directions, while reply sentences can only output one-way autoregressive. The above system improvements make the one-way generation of dialogue tasks more logical and reasonable, and the performance is better than the traditional dialogue system scheme. In consideration of the long-distance information weakness of absolute position coding, we put forward the improvement of relative position coding in theory, and verify it in subsequent experiments. In the transformer module, the calculation formula of self-attention is modified, and the relative position information is added to replace the absolute position coding of the position embedding layer. The performance of the modified model in BLEU, embedding average, grammatical and semantic coherence is ideal, to enhance long-distance attention.

Networking Global Hip Hop Knowledges: The CIPHER Method

Abstract CIPHER: Hip Hop Interpellation is a global hip hop knowledge mapping project using ethnographic, digital, and arts practice research methods to better understand the emergences and flows of the culture's deeply local yet immanently global intertextualities. In this collaborative article, we network and develop ideas from six of CIPHER's global hip hop researchers, elaborating the project in method as well as theory. In so doing, we model our community-engaged CIPHER method of tracking thematic, conceptual, and archetypal relationships, presenting preliminary findings in four interrelated case studies: examples of hip hop knowledge transfer that evidence hip hop's generative glocal dialogue.

Positioning and repositioning in higher education: first year students engaging with the world

ABSTRACT Sustainability is an important issue that we all face, including higher education students. We assert that the transition into the contemporary higher education context needs educators to plan transition pedagogy that engages students with the world during their studies, instead of solely using curriculum as preparation for the future world of work. To investigate this, we explored how students position themselves in relation to sustainability as part of an assessment task in a first-year university transition course and whether this type of assessment provides opportunities for students to experience subjectification. Drawing on Biesta’s ([2022]. World-Centred Education: A View for the Present. New York: Routledge, Taylor & Francis Group) conception of world-centred education, we applied a novel methodology based on dialogical self theory, developed by Hermans and Bartels ([2021]. Citizenship Education and the Personalization of Democracy. New York: Routledge, Taylor & Francis Group. https://lccn.loc.gov/2020029653), to analyse the data comprising student reflections on an assessment item oriented toward current sustainability issues. Our findings suggest that when students interact with their peers and encounter challenging content, conflicting internal positions can lead to subjectification and an intention for further action on real-world issues from the commencement of their studies. We propose that the principles of opposition, cooperation and participation provide a practical framework for educators and course designers to purposefully designate space for students to explore positions and practise the generative dialogue needed for thinking and acting in the world as subjects now and in the future. In analysing students’ reported experience, our paper contributes to the discussion around implementing world-centred education and provides useful insight into how students engage with sustainability in higher education.

Black Women Making Place in Nineteenth- Century Newspapers

This essay argues that letters to the editor are modes of “life storying” that document individual and collective makings of place as a collective Black feminist activism and politics. Using data visualization as a method of research and protocol of reading enables one to see that recalibrating how letters to the editor are understood, from a focus on the individual to one on the collective, reveals their political work across space and scale in the early to late nineteenth century. But digital humanities tools, such as data visualization, need to be used with attention to the foundational assumptions that underlie them and will not, alone, necessarily produce readings that put the individual and collective in generative dialogue. Rather, interscale readings that combine both foundational and new reading methodologies in the humanities may reveal more about Black women’s lives through this press form they used.

Knowledge graph assisted end-to-end medical dialog generation

Medical dialog systems have the potential to assist e-medicine in improving access to healthcare services, improving patient treatment quality, and lowering medical expenses. In this research, we describe a knowledge-grounded conversation generation model that demonstrates how large-scale medical information in the form of knowledge graphs can aid in language comprehension and generation in medical dialog systems. Generic responses are often produced by existing generative dialog systems, resulting in monotonous and uninteresting conversations. To solve this problem, we combine various pre-trained language models with a medical knowledge base (UMLS) to generate clinically correct and human-like medical conversations using the recently released MedDialog-EN dataset. The medical-specific knowledge graph contains broadly 3 types of medical-related information, including disease, symptom and laboratory test. We perform reasoning over the retrieved knowledge graph by reading the triples in each graph using MedFact attention, which allows us to use semantic information from the graphs for better response generation. In order to preserve medical information, we employ a policy network, which effectively injects relevant entities associated with each dialog into the response. We also study how transfer learning can significantly improve the performance by utilizing a relatively small corpus, created by extending the recently released CovidDialog dataset, containing the dialogs for diseases that are symptoms of Covid-19. Empirical results on the MedDialog corpus and the extended CovidDialog dataset demonstrate that our proposed model significantly outperforms the state-of-the-art methods in terms of both automatic evaluation and human judgment.

Dialogue and creativity: The generative dialogical perspective in therapy

AbstractThe generative perspective in therapy understands relations and dialogue as a generative social space where participants can promote innovative resources and possibilities for themselves, and their relations and circumstances, along with new social ecologies. It focuses on the creative dimensions of human relationality. This epistemological and clinical perspective has a heuristic value that allows us to discern and work with micro dialogues—micro processes of creative, generative dialogues—in the ongoing dialogue, mindful of the opportunities for creativity and innovation they provide. The generative perspective promotes creative processes and transformations to help clients build possible and viable futures when faced with problems, conflicts and challenges. It involves the dialogical and relational co‐creation of resources and possibilities, and actions for implementation. The perspective is illustrated with a therapy process involving a 3‐year follow‐up. The paper includes a section where differences and similarities between dialogical perspectives are presented.

Generative systemic‐constructionist psychotherapy in the face of crisis in the context of armed violence in colombia: Case of MM, Montes de María – Department of Sucre

AbstractThis article aims to show a process of systemic‐constructionist and generative therapy in the face of crisis situations experienced by MM. MM is a woman victim–survivor from the region of Los Montes de María in Colombia, a territory hard hit by armed violence between 1990 and 2008. Methodologically, the fragments presented are those that are repeated in three sessions. Psychotherapeutic work is a combination of dialogical and interactive resources, opportunities, and capacities that combine three kinds of time in MM's daily life. These are: first, the past of the violence; second, the present comprised of the presence of memories of violence, social and family interactions, together with psychiatric diagnoses; and third, the sense of a future based on the hope of reducing their suffering and taking action against the violence. Analysis and interpretation are hermeneutical constructions carried out throughout the psychotherapeutic process and in the midst of generative dialogues. On the one hand, the scientific and everyday knowledge that helps to process and transform the crisis is recognised. On the other hand, it shows a form of knowledge that distances itself from the parameters of science and positivist approaches. In conclusion, this article is an opportunity to question traditional positions within the field of mental health in the light of moments constructed with MM in the framework of systemic‐constructionist therapy, seen as a relational space where generative contexts are built.

From Domination to Dialogue and the Ethics of the Between: Transforming Human-Working Equine Relationships in Mountain Tourism

The welfare of working equines is born of the relationship co-created with humans and the relational practices humans bring to this work. Our understanding of this relationship remains elusive, however, for it involves attending to that which arises both within and between the equine and the human. Attempts to study such relationships have, arguably, been confounded by the liminalities of relational practices, power literacy and the limitations of language, propositional knowing and the dualistic thinking that characterises many scientific disciplines. This paper presents the theoretical framework that underpins an experiential awareness- based Action Research approach to transforming human-equine relations within the international mountain tourism industry. This approach privileges curiosity, compassion and primary or contemplative knowing and the development of self-awareness. Drawing on the work of Martin Buber on genuine dialogue and of Otto Scharmer on generative dialogue, this paper provides insights into what can arise in the between when attitudinal shifts are encouraged and facilitated that allow humans and equines to meet genuinely and be fully present to each other. This ultimately involves surrendering control, letting go, the dissolution of subject-object awareness and access to non-dualistic ways of knowing. An awareness of the importance of such shifts and of the source from which we operate is of fundamental importance to the realisation of the co-creative project that humans and equines can engage in. Failure to appreciate this distinction, arguably, leads and gives rise to relationships, whether human-to-human or human-to-horse, characterised by domination rather than partnering, absencing rather than presencing, by monologue rather than dialogue. The ethical and practical implications of this awareness are profound, with implications felt at the level of the individual, for whom the I deepens the more you pay attention, and at the level of the relationship, but also at the level of communities, whether these be constituted locally, nationally, internationally or indeed globally.